x86/asm: Introduce inline memcpy and memset

Provide inline memcpy and memset functions that can be used instead of
the GCC builtins when necessary. The immediate use case is for the text
poking functions to avoid the standard memcpy()/memset() calls because
objtool complains about such dynamic calls within an AC=1 region. See
tools/objtool/Documentation/objtool.txt, warning #9, regarding function
calls with UACCESS enabled.

Some user copy functions such as copy_user_generic() and __clear_user()
have similar rep_{movs,stos} usages. But, those are highly specialized
and hard to combine or reuse for other things. Define these new helpers
for all other usages that need a completely unoptimized, strictly inline
version of memcpy() or memset().

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Sohil Mehta <sohil.mehta@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://patch.msgid.link/20251118182911.2983253-4-sohil.mehta%40intel.com

arch/x86/include/asm/string.h

@@ -1,6 +1,32 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_STRING_H
+#define _ASM_X86_STRING_H
+
 #ifdef CONFIG_X86_32
 # include <asm/string_32.h>
 #else
 # include <asm/string_64.h>
 #endif
+
+static __always_inline void *__inline_memcpy(void *to, const void *from, size_t len)
+{
+	void *ret = to;
+
+	asm volatile("rep movsb"
+		     : "+D" (to), "+S" (from), "+c" (len)
+		     : : "memory");
+	return ret;
+}
+
+static __always_inline void *__inline_memset(void *s, int v, size_t n)
+{
+	void *ret = s;
+
+	asm volatile("rep stosb"
+		     : "+D" (s), "+c" (n)
+		     : "a" ((uint8_t)v)
+		     : "memory");
+	return ret;
+}
+
+#endif /* _ASM_X86_STRING_H */